Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    诚意
    -0.06
    Phi
    -0.06
    /manual
    -0.06
    them
    -0.06
    (if
    -0.06
     Tu
    -0.06
    ledon
    -0.06
    	link
    -0.06
    nął
    -0.06
     If
    -0.06
    POSITIVE LOGITS
    从来没有
    0.07
     después
    0.07
     Grocery
    0.07
    TexParameteri
    0.07
    REE
    0.06
    -chain
    0.06
     OCD
    0.06
     backpage
    0.06
    bara
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.188%

    No Known Activations